[SystemZ] Add tests for llvm.canonicalize.f(32|64).

These tests include only the floating point types supported in common code.
Once a SystemZ-specific implementation for `f16` and `f128` is available, these
tests will be expanded to include those types as well.

The tests are heavily based on the equivalent tests for X86.

Author: dominik-steenken

llvm/test/CodeGen/SystemZ/canonicalize-vars.ll

@@ -0,0 +1,131 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --default-march s390x-unknown-linux-gnu --version 5
+; RUN: llc -mtriple=s390x-linux-gnu -mcpu=z16 < %s | FileCheck %s -check-prefixes=Z16
+
+define float @canonicalize_fp32(float %a) {
+; Z16-LABEL: canonicalize_fp32:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vgmf %v1, 2, 8
+; Z16-NEXT:    meebr %f0, %f1
+; Z16-NEXT:    br %r14
+  %canonicalized = call float @llvm.canonicalize.f32(float %a)
+  ret float %canonicalized
+}
+
+define double @canonicalize_fp64(double %a) {
+; Z16-LABEL: canonicalize_fp64:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vgmg %v1, 2, 11
+; Z16-NEXT:    mdbr %f0, %f1
+; Z16-NEXT:    br %r14
+  %canonicalized = call double @llvm.canonicalize.f64(double %a)
+  ret double %canonicalized
+}
+
+define void @canonicalize_ptr_f32(float * %out) {
+; Z16-LABEL: canonicalize_ptr_f32:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vgmf %v0, 2, 8
+; Z16-NEXT:    meeb %f0, 0(%r2)
+; Z16-NEXT:    ste %f0, 0(%r2)
+; Z16-NEXT:    br %r14
+  %val = load float, float * %out
+  %canonicalized = call float @llvm.canonicalize.f32(float %val)
+  store float %canonicalized, float * %out
+  ret void
+}
+
+define void @canonicalize_ptr_f64(double * %out) {
+; Z16-LABEL: canonicalize_ptr_f64:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vgmg %v0, 2, 11
+; Z16-NEXT:    mdb %f0, 0(%r2)
+; Z16-NEXT:    std %f0, 0(%r2)
+; Z16-NEXT:    br %r14
+  %val = load double, double * %out
+  %canonicalized = call double @llvm.canonicalize.f64(double %val)
+  store double %canonicalized, double * %out
+  ret void
+}
+
+define <4 x float> @canonicalize_v4f32(<4 x float> %a) {
+; Z16-LABEL: canonicalize_v4f32:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vrepf %v0, %v24, 3
+; Z16-NEXT:    vgmf %v1, 2, 8
+; Z16-NEXT:    vrepf %v2, %v24, 2
+; Z16-NEXT:    meebr %f0, %f1
+; Z16-NEXT:    meebr %f2, %f1
+; Z16-NEXT:    vrepf %v3, %v24, 1
+; Z16-NEXT:    vmrhf %v0, %v2, %v0
+; Z16-NEXT:    wfmsb %f2, %v24, %f1
+; Z16-NEXT:    wfmsb %f1, %f3, %f1
+; Z16-NEXT:    vmrhf %v1, %v2, %v1
+; Z16-NEXT:    vmrhg %v24, %v1, %v0
+; Z16-NEXT:    br %r14
+  %canonicalized = call <4 x float> @llvm.canonicalize.v4f32(<4 x float> %a)
+  ret <4 x float> %canonicalized
+}
+
+define <4 x double> @canonicalize_v4f64(<4 x double> %a) {
+; Z16-LABEL: canonicalize_v4f64:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vgmg %v0, 2, 11
+; Z16-NEXT:    vrepg %v2, %v24, 1
+; Z16-NEXT:    wfmdb %f1, %v24, %f0
+; Z16-NEXT:    mdbr %f2, %f0
+; Z16-NEXT:    vmrhg %v24, %v1, %v2
+; Z16-NEXT:    vrepg %v2, %v26, 1
+; Z16-NEXT:    wfmdb %f1, %v26, %f0
+; Z16-NEXT:    wfmdb %f0, %f2, %f0
+; Z16-NEXT:    vmrhg %v26, %v1, %v0
+; Z16-NEXT:    br %r14
+  %canonicalized = call <4 x double> @llvm.canonicalize.v4f64(<4 x double> %a)
+  ret <4 x double> %canonicalized
+}
+
+define void @canonicalize_ptr_v4f32(<4 x float> * %out) {
+; Z16-LABEL: canonicalize_ptr_v4f32:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vl %v0, 0(%r2), 3
+; Z16-NEXT:    vrepf %v1, %v0, 3
+; Z16-NEXT:    vgmf %v2, 2, 8
+; Z16-NEXT:    vrepf %v3, %v0, 2
+; Z16-NEXT:    meebr %f1, %f2
+; Z16-NEXT:    meebr %f3, %f2
+; Z16-NEXT:    vmrhf %v1, %v3, %v1
+; Z16-NEXT:    wfmsb %f3, %f0, %f2
+; Z16-NEXT:    vrepf %v0, %v0, 1
+; Z16-NEXT:    meebr %f0, %f2
+; Z16-NEXT:    vmrhf %v0, %v3, %v0
+; Z16-NEXT:    vmrhg %v0, %v0, %v1
+; Z16-NEXT:    vst %v0, 0(%r2), 3
+; Z16-NEXT:    br %r14
+  %val = load <4 x float>, <4 x float> * %out
+  %canonicalized = call <4 x float> @llvm.canonicalize.v4f32(<4 x float> %val)
+  store <4 x float> %canonicalized, <4 x float> * %out
+  ret void
+}
+
+define void @canonicalize_ptr_v4f64(<4 x double> * %out) {
+; Z16-LABEL: canonicalize_ptr_v4f64:
+; Z16:       # %bb.0:
+; Z16-NEXT:    vl %v1, 16(%r2), 4
+; Z16-NEXT:    vgmg %v2, 2, 11
+; Z16-NEXT:    wfmdb %f3, %f1, %f2
+; Z16-NEXT:    vrepg %v1, %v1, 1
+; Z16-NEXT:    mdbr %f1, %f2
+; Z16-NEXT:    vl %v0, 0(%r2), 4
+; Z16-NEXT:    vmrhg %v1, %v3, %v1
+; Z16-NEXT:    wfmdb %f3, %f0, %f2
+; Z16-NEXT:    vrepg %v0, %v0, 1
+; Z16-NEXT:    mdbr %f0, %f2
+; Z16-NEXT:    vmrhg %v0, %v3, %v0
+; Z16-NEXT:    vst %v0, 0(%r2), 4
+; Z16-NEXT:    vst %v1, 16(%r2), 4
+; Z16-NEXT:    br %r14
+  %val = load <4 x double>, <4 x double> * %out
+  %canonicalized = call <4 x double> @llvm.canonicalize.v4f64(<4 x double> %val)
+  store <4 x double> %canonicalized, <4 x double> * %out
+  ret void
+}
+